Hybrid fine-tuning jointly optimizes LLMs and PEFT modules with mixed-order optimization and provides convergence guarantees under a new hybrid smoothness condition.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
New Hybrid Fine-Tuning Paradigm for LLMs: Algorithm Design and Convergence Analysis Framework
Hybrid fine-tuning jointly optimizes LLMs and PEFT modules with mixed-order optimization and provides convergence guarantees under a new hybrid smoothness condition.